Observability
Analytics
Analytics provide a high-level overview of how your application is using Generative AI. This includes metrics like costs, tokens, requests, latency, top models, etc.
Metrics
Metrics can be broken down by user, model, latency, status, etc. and filtered within a specific time period. The primary metrics we track are:
- Cost: Discover how expensive your LLM’s are for your business.
- Latency: Accurately measure how quick your LLM requests respond.
- Tokens: Count tokens used on input, output, and total.
- Models: View the breakdown of your model usage
- Users: Visualize how many users are active on your application
Questions or Feedback?
Have any questions or feature requests? Reach out to us at hello@puzzlet.ai